Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2700 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.7336. Min Range: -3.7336

Max Act: 3.7178. Min Act: -0.1700

Data Index: 3589305 (Open Web Text)

Max Activating Token Index: 15

Text #1

Max Range: 3.7336. Min Range: -3.7336

Max Act: 3.7336. Min Act: -0.1700

Data Index: 1549467 (Open Web Text)

Max Activating Token Index: 192

Text #2

Max Range: 3.7336. Min Range: -3.7336

Max Act: 3.6747. Min Act: -0.1700

Data Index: 4658009 (Open Web Text)

Max Activating Token Index: 34

Text #3

Max Range: 3.7336. Min Range: -3.7336

Max Act: 3.6352. Min Act: -0.1700

Data Index: 6034050 (Open Web Text)

Max Activating Token Index: 654

Text #4

Max Range: 3.7336. Min Range: -3.7336

Max Act: 3.6175. Min Act: -0.1700

Data Index: 2447697 (Open Web Text)

Max Activating Token Index: 899

Text #5

Max Range: 3.7336. Min Range: -3.7336

Max Act: 3.6499. Min Act: -0.1700

Data Index: 4831515 (Open Web Text)

Max Activating Token Index: 79

Text #6

Max Range: 3.7336. Min Range: -3.7336

Max Act: 3.6166. Min Act: -0.1700

Data Index: 8298366 (Open Web Text)

Max Activating Token Index: 14

Text #7

Max Range: 3.7336. Min Range: -3.7336

Max Act: 3.5686. Min Act: -0.1700

Data Index: 5159529 (Open Web Text)

Max Activating Token Index: 85

Text #8

Max Range: 3.7336. Min Range: -3.7336

Max Act: 3.5782. Min Act: -0.1700

Data Index: 4257786 (Open Web Text)

Max Activating Token Index: 713

Text #9

Max Range: 3.7336. Min Range: -3.7336

Max Act: 3.5419. Min Act: -0.1700

Data Index: 7719665 (Open Web Text)

Max Activating Token Index: 208

Text #10

Max Range: 3.7336. Min Range: -3.7336

Max Act: 3.5332. Min Act: -0.1700

Data Index: 8319163 (Open Web Text)

Max Activating Token Index: 84

Text #11

Max Range: 3.7336. Min Range: -3.7336

Max Act: 3.5334. Min Act: -0.1700

Data Index: 2887414 (Open Web Text)

Max Activating Token Index: 150

Text #12

Max Range: 3.7336. Min Range: -3.7336

Max Act: 3.5292. Min Act: -0.1700

Data Index: 7411662 (Open Web Text)

Max Activating Token Index: 43

Text #13

Max Range: 3.7336. Min Range: -3.7336

Max Act: 3.5263. Min Act: -0.1700

Data Index: 3561552 (Open Web Text)

Max Activating Token Index: 24

Text #14

Max Range: 3.7336. Min Range: -3.7336

Max Act: 3.5365. Min Act: -0.1700

Data Index: 3573322 (Open Web Text)

Max Activating Token Index: 517

Text #15

Max Range: 3.7336. Min Range: -3.7336

Max Act: 3.5300. Min Act: -0.1700

Data Index: 6041607 (Open Web Text)

Max Activating Token Index: 96

Text #16

Max Range: 3.7336. Min Range: -3.7336

Max Act: 3.5074. Min Act: -0.1700

Data Index: 3133264 (Open Web Text)

Max Activating Token Index: 465

Text #17

Max Range: 3.7336. Min Range: -3.7336

Max Act: 3.5175. Min Act: -0.1700

Data Index: 1139792 (Open Web Text)

Max Activating Token Index: 319

Text #18

Max Range: 3.7336. Min Range: -3.7336

Max Act: 3.5191. Min Act: -0.1700

Data Index: 3384688 (Open Web Text)

Max Activating Token Index: 18

Text #19

Max Range: 3.7336. Min Range: -3.7336

Max Act: 3.4946. Min Act: -0.1700

Data Index: 1595898 (Open Web Text)

Max Activating Token Index: 1002